Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly/idempotent/openWorld safety; the description adds substantial context beyond that: it discloses the output risk tiers (low/medium/high), that the method is heuristic (signalling possible false positives), and the exact cost model — 10 free calls/day, then $0.001/call via x402 params._meta or X-API-Key. Pricing and rate limits are precisely the kind of invocation-critical behavior an agent cannot infer from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the scan scope and detection categories, then detection tiers, then commercial terms — a sensible ordering with no filler sentences. The payment sentence is dense with mechanics (x402 path, header, credits) and reads as compressed, but each clause is actionable rather than decorative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value structure need not be explained; the description instead covers the three things an agent still needs — what content to submit, what classes of risk are detected, and what the call will cost or require for authentication. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning by specifying that the single `text` parameter should be untrusted content sourced from web pages, email, or tool output rather than arbitrary input. That is modest but genuine guidance beyond the schema's terse 'untrusted text'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Heuristic scan') and resource ('untrusted web/email/tool content') and enumerates the exact marker classes detected: instruction override, system-prompt spoofing, secret exfiltration, payment coercion, hidden Unicode, image-URL exfil. No sibling tool in the catalog performs content-risk scanning, and the description makes the boundary unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly scopes the input to untrusted content from web, email, or tool output, which tells an agent when this tool applies. It stops short of explicit when-not guidance (e.g. skipping trusted content or local sanitization already performed), but the input-scope framing is strong enough to route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.